def _job_shares(n_jobs, trials):
if n_jobs == -1:
n_jobs = cpu_count()
shares = [trials // n_jobs] * n_jobs
for i in range(trials - sum(shares)):
shares[i] += 1
return shares
def _job_shares(n_jobs, trials):
if n_jobs == -1:
n_jobs = cpu_count()
shares = [trials // n_jobs] * n_jobs
for i in range(trials - sum(shares)):
shares[i] += 1
return shares
def _hdbscan_boruvka_balltree(X, min_samples=5, alpha=1.0,
metric='minkowski', p=2, leaf_size=40,
approx_min_span_tree=True,
gen_min_span_tree=False,
core_dist_n_jobs=4, **kwargs):
if leaf_size < 3:
leaf_size = 3
if core_dist_n_jobs < 1:
core_dist_n_jobs = max(cpu_count() + 1 + core_dist_n_jobs, 1)
if X.dtype != np.float64:
X = X.astype(np.float64)
tree = BallTree(X, metric=metric, leaf_size=leaf_size, **kwargs)
alg = BallTreeBoruvkaAlgorithm(tree, min_samples, metric=metric,
leaf_size=leaf_size // 3,
approx_min_span_tree=approx_min_span_tree,
n_jobs=core_dist_n_jobs, **kwargs)
min_spanning_tree = alg.spanning_tree()
# Sort edges of the min_spanning_tree by weight
min_spanning_tree = min_spanning_tree[np.argsort(min_spanning_tree.T[2]),
:]
# Convert edge list into standard hierarchical clustering format
single_linkage_tree = label(min_spanning_tree)
if gen_min_span_tree:
return single_linkage_tree, min_spanning_tree
else:
return single_linkage_tree, None
def _get_n_jobs(n_jobs):
"""Get number of jobs for the computation.
See sklearn/utils/__init__.py for more information.
This function reimplements the logic of joblib to determine the actual
number of jobs depending on the cpu count. If -1 all CPUs are used.
If 1 is given, no parallel computing code is used at all, which is useful
for debugging. For n_jobs below -1, (n_cpus + 1 + n_jobs) are used.
Thus for n_jobs = -2, all CPUs but one are used.
Parameters
----------
n_jobs : int
Number of jobs stated in joblib convention.
Returns
-------
n_jobs : int
The actual number of jobs as positive integer.
Examples
--------
>>> from sklearn.utils import _get_n_jobs
>>> _get_n_jobs(4)
4
>>> jobs = _get_n_jobs(-2)
>>> assert jobs == max(cpu_count() - 1, 1)
>>> _get_n_jobs(0)
Traceback (most recent call last):
...
ValueError: Parameter n_jobs == 0 has no meaning.
"""
if n_jobs < 0:
return max(cpu_count() + 1 + n_jobs, 1)
elif n_jobs == 0:
raise ValueError('Parameter n_jobs == 0 has no meaning.')
else:
return n_jobs
def compute_geodesic_distance_matrix(verts, tris):
print "precomputing geodesic distance..."
n_chunks = cpu_count()
chunk_size = int(np.ceil(len(verts) / float(n_chunks)))
sources = np.arange(len(verts))
D = Parallel(n_chunks)(
delayed(compute_geodesic_distances)(verts, tris, sources[i: i + chunk_size])
for i in xrange(0, len(verts), chunk_size))
return np.vstack(D)
def compute_geodesic_distance_matrix(verts, tris):
print "precomputing geodesic distance..."
n_chunks = cpu_count()
chunk_size = int(np.ceil(len(verts) / float(n_chunks)))
sources = np.arange(len(verts))
D = Parallel(n_chunks)(
delayed(compute_geodesic_distances)(verts, tris, sources[i:i +
chunk_size])
for i in xrange(0, len(verts), chunk_size))
return np.vstack(D)
def junction_make(config, *args, **kwargs):
click.echo(green_fg("\n{} Junction Make {}\n".format(">" * 10,
"<" * 10)))
threads = kwargs['threads'] if kwargs['threads'] else parallel.cpu_count()
input_data_folder = 'unmapped_sam_files' if kwargs[
'unmapped'] else 'sam_files'
junction_folder = 'junction_files' # Manage name of junction reads output folder here
blast_results_folder = 'blast_results' # Manage name of blast results output folder here
blast_results_query = 'blast_results_query' # Manage name of blast results dictionary output folder here
junction_sequence = junction_sequences[kwargs['genome']].replace(
" ", "").split(",")
if kwargs['seq'] != "":
junction_sequence = kwargs['seq'].replace(" ", "").split(",")
exclusion_sequence = kwargs['exclude_seq'].replace(" ", "")
blast_db = blast_dbs[kwargs['genome']]
gene_list_file = gene_lists[kwargs['genome']]
# verify if the options provided are valid
verify_options(*args, **kwargs)
# create folders for junction make
check_and_create_folders(
kwargs['dir'],
['junction_files', 'blast_results', 'blast_results_query'],
interactive=kwargs['interactive'])
if kwargs['interactive']:
if not click.confirm(
magenta_fg('\nDo you want to search junctions and blast?')):
click.echo(red_fg("...Skipping search junctions and blast..."))
else:
# search for junctions
junction_search(kwargs['dir'], junction_folder, input_data_folder,
blast_results_folder, junction_sequence,
exclusion_sequence, threads)
# blast the junctions
blast_search(kwargs['dir'], blast_db, blast_results_folder)
if not click.confirm(
magenta_fg('\nDo you want to parse blast results')):
click.echo(red_fg("ABORTING..."))
sys.exit(1)
else:
# parse blast results
parse_blast_results(kwargs['dir'], blast_results_folder,
blast_results_query, gene_list_file, threads)
else:
# search for junctions
junction_search(kwargs['dir'], junction_folder, input_data_folder,
blast_results_folder, junction_sequence,
exclusion_sequence, threads)
# blast the junctions
blast_search(kwargs['dir'], blast_db, blast_results_folder)
# parse blast results
parse_blast_results(kwargs['dir'], blast_results_folder,
blast_results_query, gene_list_file, threads)
def test_nested_parallelism_limit(backend):
with parallel_backend(backend, n_jobs=2):
backend_types_and_levels = _recursive_backend_info()
if cpu_count() == 1:
second_level_backend_type = 'SequentialBackend'
else:
second_level_backend_type = 'ThreadingBackend'
top_level_backend_type = backend.title() + 'Backend'
expected_types_and_levels = [
(top_level_backend_type, 0),
(second_level_backend_type, 1),
('SequentialBackend', 2),
('SequentialBackend', 3)
]
assert backend_types_and_levels == expected_types_and_levels
def _calculate_n_jobs_and_actual_iters(self):
# because HpBandSter assigns n_iter jobs to each worker, we need to divide
n_jobs = self.n_jobs
if not n_jobs:
n_jobs = 1
elif n_jobs < 0:
try:
import psutil
cpus = int(
os.environ.get("LOKY_MAX_CPU_COUNT",
psutil.cpu_count(logical=False)))
except:
cpus = cpu_count()
n_jobs = max(cpus + 1 + n_jobs, 1)
if n_jobs > self.n_iter:
n_jobs = self.n_iter
actual_iterations = self.n_iter // n_jobs + (self.n_iter % n_jobs > 0)
return (n_jobs, actual_iterations)
def blast_search(directory, db_name, blast_results_folder):
suffix = ''
if _platform.startswith('win'):
suffix = '.exe'
blast_path = os.path.join(os.path.expanduser('~'), ".deepn", "data",
"blast")
db_path = os.path.join(os.path.expanduser('~'), ".deepn", db_name)
click.echo(green_fg("\n>>> Selected Blast DB: %s" % db_name))
file_list = get_file_list(directory, blast_results_folder, ".fa")
for file_name in file_list:
if not os.path.getsize(
os.path.join(directory, blast_results_folder, file_name)) == 0:
start = time.time()
output_file = os.path.join(
directory, blast_results_folder,
file_name.replace(".junctions.fa", '.blast.txt'))
click.echo(
yellow_fg("\n>>> Running BLAST search for file: " + file_name))
blast_command_list = [
os.path.join(blast_path, 'blastn' + suffix), '-query',
os.path.join(directory, blast_results_folder,
file_name), '-db', db_path, '-task', 'blastn',
'-dust', 'no', '-num_threads',
str(parallel.cpu_count()), '-outfmt', '7', '-out', output_file,
'-evalue', '0.2', '-max_target_seqs', '10'
]
blast_pipe = subprocess.Popen(blast_command_list, shell=False)
blast_pipe.wait()
finish = time.time()
hr, min, sec = elapsed_time(start, finish)
click.echo(
cyan_fg(
"\nFinished blasting file %s in time %d hr, %d min, %d sec"
% (file_name, hr, min, sec)))
else:
click.echo(
red_fg("\n>>> ERROR: File %s does not have any junctions, "
"please check if they right genome was chosen." %
file_name))
sys.exit(1)
num_mutations = randint(1, max_mutations)
for mutation in range(num_mutations):
street = choice(streets)
idx = choice(street)
chromosome[idx] = randint(0, 6)
return key_chromosome(chromosome)
if __name__ == '__main__':
population_size = 50
nr_populations = 10
remain_perc = 0.2
mutate_perc = 0.01
population_size = cpu_count() * ((population_size / cpu_count()) + 1)
population = set(generate_random() for _ in xrange(population_size))
evaluated = {}
for generation in range(1, nr_populations + 1):
results = Parallel(n_jobs=-1, verbose=100)(delayed(calculate)(chromosome, buy_all) for chromosome in population)
for score, chromosome in results:
evaluated[chromosome] = score
winners = []
for chromosome, score in evaluated.iteritems():
winners.append((score, chromosome))
winners.sort(reverse=True)
def test_cpu_count():
assert cpu_count() > 0
def test_cpu_count():
assert cpu_count() > 0
for mutation in range(num_mutations):
street = choice(streets)
idx = choice(street)
chromosome[idx] = randint(0, 6)
return key_chromosome(chromosome)
if __name__ == '__main__':
population_size = 50
nr_populations = 25
remain_perc = 0.2
mutate_perc = 0.01
population_size = cpu_count() * ((population_size / cpu_count()) + 1)
population = set(generate_random() for _ in xrange(population_size))
population.add(buy_all)
# population.add(key_chromosome(map(int, '0,6,0,5,0,2,4,0,4,4,0,6,0,5,5,2,4,0,5,3,0,0,0,0,0,2,0,0,0,0,0,0,0,0,0,4,0,5,0,3'.split(","))))
# population.add(key_chromosome(map(int, '0,6,0,6,0,4,4,0,4,4,0,3,0,5,5,3,4,0,5,6,0,0,0,0,0,2,0,0,0,0,0,0,0,0,0,4,0,5,0,2'.split(","))))
for generation in range(1, nr_populations + 1):
to_schedule = []
for chromosome in population:
get_player_stats(chromosome)
for chromosome in population:
opponents = [
buy_all,
class Significance(object):
"""Test for pairwise significance between systems"""
METHODS = {
'permute': count_permutation_trials,
#'bootstrap': count_bootstrap_trials,
}
def __init__(self,
systems,
gold,
trials=10000,
method='permute',
n_jobs=1,
metrics=['precision', 'recall', 'fscore'],
fmt='json'):
if len(systems) < 2:
raise ValueError('Require at least two systems to compare')
if method not in self.METHODS:
raise ValueError('Unsupported method: {}'.format(method))
# Check whether import worked, generate a more useful error.
if Parallel is None:
raise ImportError(
'Package: "joblib" not available, please install to run significance tests.'
)
self.systems = systems
self.gold = gold
self.method = method
self.trials = trials
self.n_jobs = n_jobs
self.metrics = metrics
self.fmt = FMTS[fmt] if fmt is not callable else fmt
def __call__(self):
all_counts = defaultdict(dict)
gold = sorted(Reader(open(self.gold)))
for path in self.systems:
system = sorted(Reader(open(path)))
for match, per_doc, overall in Evaluate.count_all(system, gold):
all_counts[match][path] = (per_doc, overall)
results = [
{
'sys1': sys1,
'sys2': sys2,
'match': match,
'stats': self.significance(match_counts[sys1],
match_counts[sys2])
} for sys1, sys2 in itertools.combinations(self.systems, 2)
for match, match_counts in sorted(
all_counts.iteritems(), key=lambda (k, v): MATCHES.index(k))
]
return self.fmt(results, self.metrics)
def significance(self, (per_doc1, overall1), (per_doc2, overall2)):
# TODO: limit to metrics
base_diff = _result_diff(overall1, overall2)
randomized_diffs = functools.partial(self.METHODS[self.method],
per_doc1, per_doc2, base_diff)
n_jobs = self.n_jobs
if n_jobs == -1:
n_jobs = cpu_count()
shares = [self.trials // n_jobs] * n_jobs
for i in range(self.trials - sum(shares)):
shares[i] += 1
results = Parallel(n_jobs=self.n_jobs)(delayed(randomized_diffs)(share)
for share in shares)
all_counts = []
for result in results:
metrics, counts = zip(*result.iteritems())
all_counts.append(counts)
return {
metric: {
'diff': base_diff[metric],
'p': (sum(counts) + 1) / (self.trials + 1)
}
for metric, counts in zip(metrics, zip(*all_counts))
}
def druhg(X,
max_ranking=16,
limit1=None,
limit2=None,
exclude=None,
fix_outliers=0,
metric='minkowski',
p=2,
algorithm='best',
leaf_size=40,
verbose=False,
core_n_jobs=None,
**kwargs):
"""Perform DRUHG clustering from a vector array or distance matrix.
Parameters
----------
X : array matrix of shape (n_samples, n_features), or \
array of shape (n_samples, n_samples)
A feature array, or array of distances between samples if
``metric='precomputed'``.
max_ranking : int, optional (default=15)
The maximum number of neighbors to search.
Affects performance vs precision.
limit1 : float, optional (default=sqrt(size))
Clusters that are smaller than this limit treated as noise.
Use 1 to find True outliers.
Numbers under 1 treated as percentage of the dataset size
limit2 : float, optional (default=size/2)
Clusters with size OVER this limit treated as noise.
Use it to break down big clusters.
Numbers under 1 treated as percentage of the dataset size
exclude: list, optional (default=None)
Clusters with these indexes would not be formed.
Use it for surgical cluster removal.
fix_outliers: int, optional (default=0)
In case of 1 - all outliers will be assigned to the nearest cluster
metric : string or callable, optional (default='minkowski')
The metric to use when calculating distance between instances in a
feature array. If metric is a string or callable, it must be one of
the options allowed by metrics.pairwise.pairwise_distances for its
metric parameter.
If metric is "precomputed", X is assumed to be a distance matrix and
must be square.
p : int, optional (default=2)
p value to use if using the minkowski metric.
leaf_size : int, optional (default=40)
Leaf size for trees responsible for fast nearest
neighbour queries.
algorithm : string, optional (default='best')
Exactly, which algorithm to use; DRUHG has variants specialized
for different characteristics of the data. By default, this is set
to ``best`` which chooses the "best" algorithm given the nature of
the data. You can force other options if you believe you know
better. Options are:
* ``best``
* ``kdtree``
* ``balltree``
If you want it to be accurate add:
* ``slow``
core_n_jobs : int, optional (default=None)
Number of parallel jobs to run in neighbors distance computations (if
supported by the specific algorithm).
For default, (n_cpus + 1 + core_dist_n_jobs) is used.
**kwargs : optional
Arguments passed to the distance metric
Returns
-------
labels : ndarray, shape (n_samples)
Cluster labels for each point. Noisy samples are given the label -1.
min_spanning_tree : ndarray, shape (2*n_samples - 2)
The minimum spanning tree as edgepairs.
values_edges : ndarray, shape (n_samples - 1)
Values of the edges.
References
----------
None
"""
if type(X) is list:
raise ValueError('X must be array! Not a list!')
size = X.shape[0]
if core_n_jobs is None:
core_n_jobs = max(cpu_count(), 1)
elif core_n_jobs < 0:
core_n_jobs = max(cpu_count() + 1 + core_n_jobs, 1)
if max_ranking is not None:
if type(max_ranking) is not int:
raise ValueError('Max ranking must be integer!')
if max_ranking < 0:
raise ValueError('Max ranking must be non-negative integer!')
if leaf_size < 1:
raise ValueError('Leaf size must be greater than 0!')
if metric == 'minkowski':
if p is None:
raise TypeError('Minkowski metric given but no p value supplied!')
if p < 0:
raise ValueError('Minkowski metric with negative p value is not'
' defined!')
printout = ''
if max_ranking is None:
max_ranking = 16
printout += 'max_ranking is set to ' + str(max_ranking) + ', '
max_ranking = min(size - 1, max_ranking)
if limit1 is None:
limit1 = int(np.sqrt(size))
printout += 'limit1 is set to ' + str(limit1) + ', '
else:
if limit1 < 0:
raise ValueError('Limit1 must be non-negative integer!')
if limit1 < 1:
limit1 = int(limit1 * size)
if limit2 is None:
limit2 = int(size / 2 + 1)
printout += 'limit2 is set to ' + str(limit2) + ', '
else:
if limit2 < 0:
raise ValueError('Limit2 must be non-negative integer!')
if limit2 <= 1:
limit2 = int(limit2 * size + 1)
if algorithm == 'best':
algorithm = 'kd_tree'
if X.dtype != np.float64:
print('Converting data to numpy float64')
X = X.astype(np.float64)
algo_code = 0
if "precomputed" in algorithm.lower() or "precomputed" in metric.lower(
) or issparse(X):
algo_code = 2
if issparse(X):
algo_code = 3
elif len(X.shape) == 2 and X.shape[0] != X.shape[1]:
raise ValueError('Precomputed matrix is not a square.')
tree = X
else:
# The Cython routines used require contiguous arrays
if not X.flags['C_CONTIGUOUS']:
X = np.array(X, dtype=np.double, order='C')
if "kd" in algorithm.lower() and "tree" in algorithm.lower():
algo_code = 0
if metric not in KDTree.valid_metrics:
raise ValueError('Metric: %s\n'
'Cannot be used with KDTree' % metric)
tree = KDTree(X, metric=metric, leaf_size=leaf_size, **kwargs)
elif "ball" in algorithm.lower() and "tree" in algorithm.lower():
algo_code = 1
tree = BallTree(X, metric=metric, leaf_size=leaf_size, **kwargs)
else:
algo_code = 0
if metric not in KDTree.valid_metrics:
raise ValueError('Metric: %s\n'
'Cannot be used with KDTree' % metric)
tree = KDTree(X, metric=metric, leaf_size=leaf_size, **kwargs)
# raise TypeError('Unknown algorithm type %s specified' % algorithm)
is_slow_and_deterministic = 0
if "slow" in algorithm.lower():
is_slow_and_deterministic = 1
if printout:
print('Druhg is using defaults for: ' + printout)
ur = UniversalReciprocity(algo_code,
tree,
max_neighbors_search=max_ranking,
metric=metric,
leaf_size=leaf_size // 3,
is_slow=is_slow_and_deterministic,
n_jobs=core_n_jobs,
**kwargs)
pairs, values = ur.get_tree()
labels = label(pairs,
values,
size,
exclude=exclude,
limit1=int(limit1),
limit2=int(limit2),
fix_outliers=fix_outliers)
return (labels, pairs, values)
